Back to skill

Security audit

Pans Deal Coach

Security checks for vulnerabilities and agentic risk

Overview

This is a local sales-coaching helper that appears coherent and does not show hidden access, persistence, network use, or destructive behavior.

Install this if you want a local Chinese-first sales objection coaching tool. Review the generated claims before using them with customers, since the templates include specific performance, certification, and SLA statements that may need verification for your actual product.

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs
Vulnerability Patterns
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (4)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The trigger list includes broad phrases such as '销售教练', '客户异议', and '应对策略', which are common in ordinary business conversations and can cause the skill to activate unintentionally. Over-broad invocation expands the skill’s reach beyond explicit user intent, increasing the chance of inappropriate context capture, confusing responses, or unrequested behavioral steering in unrelated chats.

Content

No source excerpt is available for this finding.

Ae4

Medium
Category
analysis-evasion
Confidence
80% confidence
Finding

Suspicious Unicode normalization or mixed-script content

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
91% confidence
Finding

The class initializes with lang="zh", making Chinese the default output language. Although a --lang option exists, the default behavior still imposes a specific locale without user opt-in, which matches the policy concern for forced language defaults.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
95% confidence
Finding

The --lang argument offers both zh and en, but sets default="zh", so users receive Chinese output unless they explicitly override it. This is a natural-language locale policy issue because the tool enforces a specific language by default rather than offering an opt-in choice.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.